MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It transforms implicit model reasoning into explicit, event-triggered steps, enabling weaker models to operate near frontier level through lean always-loaded rules and extensive on-demand playbooks, with compliance verified by greppable markers.
Who it is for
- Developers using Claude Code for coding tasks
- Teams integrating AI assistants into software development workflows
- Power users seeking to minimize AI-generated errors and token inefficiency
Use cases
- Improving code quality and reducing bugs in AI-generated code
- Maintaining consistent planning and verification procedures across sessions
- Debugging and tracing AI reasoning with structured logs and checkpoints
Strengths
- Lean core (~45 kit lines) plus on-demand docs keeps token overhead low while providing deep coverage
- Event-phrased routing ensures relevant docs are read exactly when needed, not by topic labels
- Number-based thresholds (e.g. '10 messages', '>50 hits') enable mechanical compliance over judgment
- Prohibitions always include a named replacement to prevent workarounds
Considerations
- Requires manual installation and configuration per project
- Effectiveness depends on the model's ability to follow explicit rules and markers
- May introduce overhead for simple tasks where the full procedure is unnecessary
README quick start
Guardrails Kit v1.0
A portable CLAUDE.md + documentation set that makes Claude Opus / Sonnet operate as close to frontier (Fable) level as possible inside Claude Code: fewer logic errors, fewer introduced bugs, fewer wasted tokens. It works by converting the implicit judgment a stronger model applies automatically into explicit, checkable, event-triggered procedures a weaker model can execute mechanically.
What's in the kit
| File | Role |
|---|---|
CLAUDE.md | Always-loaded core: 12 iron rules, an event-phrased routing table, 4 hard stops. Deliberately small (~45 kit lines, hard cap 60) — always-on compliance is roughly constant-sum, so every extra line taxes obedience to all the others. |
docs/guardrails/PLAN.md | Before starting non-trivial work: TASK block, premise check, prior-art search, baseline, decomposition, ask-vs-decide. |
docs/guardrails/CODE.md | While editing: read-before-edit gates, twin/generated-file checks, and the REFERENCE SWEEP procedure (RS1-RS5). |
docs/guardrails/TRAPS.md | Lookup tables for the classic reasoning traps: dates, epochs, mutation-vs-copy, async, floats/money, sort, division/modulo, regex, familiar-API lookalikes, closures, boolean logic. Read on demand via CODE.md C7. |
docs/guardrails/DEBUG.md | When anything fails: reproduce-first loop, CAUSE line, failed-attempts ledger with the ESCALATION LADDER, red-flag table keyed on the model's own rationalization phrases. |
docs/guardrails/VERIFY.md | Before claiming done/committing: 12-item echo protocol — every claim needs output quoted from a real tool result in the same turn. |
docs/guardrails/EFFICIENCY.md | Token/context discipline as paired rules: every "read less" rule has a "read enough" floor. |
docs/guardrails/SESSION.md | Long-session survival: docs/STATE.md template (S2), same-turn update triggers (S3), post-compaction recovery (S1), ANCHOR/DETOUR/DECISION ledger keywords. |
docs/guardrails/_FORMAT.md | Authoring contracts for editing the kit itself (budgets, trigger phrasing, single-sourcing, sanctioned iron-rule pairs). |
MIGRATE.md | The transport procedure for retrofitting a project that already has a CLAUDE.md — line-accounted, backup-first, verbatim-carry, user-checkpointed, idempotent, with an UPGRADE mode. |
Not part of the installable kit (kit-source materials only): docs/research-digest.md
(the 155-findin
Description
A Fable written Claude MD for Opus/Sonnet to give it some of the quality methodology that Fable uses
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.